Research Focus
Focus of our research is the implementation of databases on modern hardware architectures. This includes “standard” architectures—such as general-purpose machines with many cores and/or deep memory hierarchies—, but also specialized processors/accelerators.
We demonstrated how query compilation or database/operating system co-design can better leverage the potential of modern multi-core hardware; or how prefetching can minimize memory access latencies. We max out the capabilities of modern storage technologies (such as, e.g., flash media) or design indexing techniques for novel storage media. We're pioneers in the use of field-programmable gate arrays (FPGAs) for database acceleration and we showed how modern network cards with hardware acceleration (by means of remote direct memory access, RDMA) can be leveraged for distributed data processing.
Current projects
Completed projects
Real-time analysis and storage for high-volume data from particle physics
SFB 876 (C05)
Algorithmics of learning methods in embedded systems
SFB 876 (A02)
Avalanche
Stream Processing on Bare Metal
In-Memory Joins
RAPP Center
Ruhr Astroparticle and Plasma Physics Center
Data Cyclotron
Data Processing on Hardware-Accelerated Networks
Pathfinder: XQuery Compilation
XQuery Compilation Techniques for relational Database Targets